Oracle Noise optimizes diffusion model noise on a Riemannian hypersphere guided by key prompt words to preserve the Gaussian prior, eliminate norm inflation, and achieve faster semantic alignment than Euclidean methods.
The silent assistant: Noisequery as implicit guidance for goal-driven image generation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3roles
dataset 1polarities
use dataset 1representative citing papers
RF-Sampling enhances flow matching models by implicitly performing gradient ascent on text-image alignment scores via linear textual combinations and flow inversion.
InterCMDM proposes a block-causal latent diffusion framework with dual-stream causal transformers and multi-task attention masks for autoregressive text-conditioned two-person interaction generation and reports SOTA results on InterHuman and Inter-X.
citing papers explorer
-
Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization
Oracle Noise optimizes diffusion model noise on a Riemannian hypersphere guided by key prompt words to preserve the Gaussian prior, eliminate norm inflation, and achieve faster semantic alignment than Euclidean methods.
-
Reflective Flow Sampling Enhancement
RF-Sampling enhances flow matching models by implicitly performing gradient ascent on text-image alignment scores via linear textual combinations and flow inversion.
-
InterCMDM: Block-Causal Diffusion for Autoregressive Human Interaction Generation
InterCMDM proposes a block-causal latent diffusion framework with dual-stream causal transformers and multi-task attention masks for autoregressive text-conditioned two-person interaction generation and reports SOTA results on InterHuman and Inter-X.